Volatility modelling in the multivariate case is becoming an important area of study as the world becomes increasingly more integrated and as barriers to entry in frontier markets come down. Understanding how frontier markets in the African region behave in contrast to those in developed markets is vital in driving portfolio allocation decisions as well as regulatory interventions.In this study we investigate the co-movements of the stock indices of four African countries, Nigeria, Morocco, Mauritius and Kenya using various multi-variate volatility models in relation to those of South Africa and the United Kingdom. We also fit a Kalman filter to the data set and examine the goodness of fit of the two approaches. For the Multi-variate models we fit an Exponentially Weighted Moving Average (EWMA) model, two specifications of Dynamic Conditional Correlation (DCC) models as well as a multivariate volatility model based on Cholesky Decomposition. We use a dynamic linear specification of the Kalman filter to allow for time-varying variances, and generate forecasts. Empirical results show that the diagnostic tests with upper tail trimming reject the EWMA model while both specifications of the DCC model as well as a multivariate model based on Cholesky decomposition is found to be adequate. Kalman filters also provide adequate modelling for each return series on the basis of assessment of residuals.